learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6853	1.0	31	0.6636	0.7143
0.706	2.0	62	0.6024	0.7143
0.681	3.0	93	0.6152	0.7143
0.6871	4.0	124	0.6462	0.7143
0.6656	5.0	155	0.6124	0.7143
0.6782	6.0	186	0.6151	0.7143
0.6889	7.0	217	0.6671	0.7143
0.6267	8.0	248	0.6076	0.7143
0.6768	9.0	279	0.6093	0.7143
0.6762	10.0	310	0.6150	0.7143
0.7003	11.0	341	0.6177	0.7143
0.685	12.0	372	0.6018	0.7143
0.6524	13.0	403	0.6105	0.7143
0.6508	14.0	434	0.6178	0.7143
0.8111	15.0	465	0.6101	0.7143
0.6728	16.0	496	0.6128	0.7143
0.6346	17.0	527	0.6183	0.7143
0.758	18.0	558	0.6007	0.7143
0.6756	19.0	589	0.6102	0.7143
0.603	20.0	620	0.6116	0.7143
0.8049	21.0	651	0.6042	0.7143
0.6767	22.0	682	0.6077	0.7143
0.7293	23.0	713	0.6138	0.7143
0.6312	24.0	744	0.6200	0.7143
0.7158	25.0	775	0.6202	0.7143
0.6508	26.0	806	0.6177	0.7143
0.722	27.0	837	0.6150	0.7143
0.6738	28.0	868	0.6160	0.7143
0.7221	29.0	899	0.6143	0.7143
0.5777	30.0	930	0.6146	0.7143

HKeren/distilhubert-finetuned-pulse-train_batch4-epochs30

distilhubert-finetuned-pulse-train_batch4-epochs30